Differential phospho analysis - CRC Batch 2 Set 2
Sophie Herbst
Analysis date: 2023-10-18
Depends on
CRC_Xenografts_Batch2_DataProcessing Script
load("../Data/Cache/Xenografts_Batch2_DataProcessing.RData")TODO
Setup
Load libraries and functions
Analysis
DEP
Tyrosine
E vs ctrl
data_diff_E_vs_ctrl_pY <- test_diff(pY_se_Set2, type="manual", test = "E_vs_ctrl")## Tested contrasts: E_vs_ctrldep_E_vs_ctrl_pY <- add_rejections_SH(data_diff_E_vs_ctrl_pY, alpha = 0.05, lfc = log2(1.2))
GGPlotly_Volcano(dep_E_vs_ctrl_pY, contrast = "E_vs_ctrl",
add_names = TRUE,
additional_title = "pY") Return_DEP_Hits_Plots(data = pY_Set2_form, dep_E_vs_ctrl_pY, comparison = "E_vs_ctrl_diff")## 'select()' returned 1:many mapping between keys and columns## Loading required namespace: reactome.db## 'select()' returned 1:many mapping between keys and columns## 'select()' returned 1:1 mapping between keys and columns
## character(0)PTM-SEA
GSEA_E_vs_ctrl_PTM <- Run_GSEA(DEP_result = dep_E_vs_ctrl_pY, comparison = "E_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T)## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "PATH-NP_EGFR1_PATHWAY"GSEA_E_vs_ctrl_PTM %>% as_tibble() %>% filter(padj < 0.05) %>% arrange(desc(NES))## # A tibble: 1 × 8
## pathway pval padj log2err ES NES size leadingEdge
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <int> <list>
## 1 PATH-NP_EGFR1_PATHWAY 0.00000702 0.00247 0.611 0.535 1.58 116 <chr [48]>Run_GSEA(DEP_result = dep_E_vs_ctrl_pY, comparison = "E_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "PATH-NP_EGFR1_PATHWAY")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "PATH-NP_EGFR1_PATHWAY"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 254 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 PXN VGEEEHVySFPNK Y118-p 2.34
## 2 PXN vGEEEHVySFPNk Y118-p 2.34
## 3 NEDD9 DGVyDVPLHNPPDAK Y345-p 2.27
## 4 CTTN LPSSPVyEDAASFK Y421-p 1.60
## 5 CTTN lPSSPVyEDAASFk Y421-p 1.60
## 6 CTTN TQTPPVSPAPQPTEERLPSSPVyEDAASFK Y421-p 1.60
## 7 GAB1 KDASSQDCyDIPR Y406-p 1.59
## 8 NCK1 LyDLNMPAYVK Y105-p 1.56
## 9 NCK1 lyDLNMPAYVk Y105-p 1.56
## 10 TNS3 KLSLGQyDNDAGGQLPFSK Y780-p 1.53
## # ℹ 244 more rowsRun_GSEA(DEP_result = dep_E_vs_ctrl_pY, comparison = "E_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "KINASE-PSP_Src/SRC")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "PATH-NP_EGFR1_PATHWAY"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 78 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 SHC1 ELFDDPSyVNVQNLDK Y427-p 1.45
## 2 SHC1 eLFDDPSyVNVQNLDk Y427-p 1.45
## 3 PRKCD KTGVAGEDMQDNSGTyGK Y334-p 1.38
## 4 PRKCD TGVAGEDMQDNSGTyGK Y334-p 1.38
## 5 PRKCD tGVAGEDMQDNSGTyGk Y334-p 1.38
## 6 PXN FIHQQPQSSSPVyGSSAK Y88-p 1.36
## 7 CTTN NASTFEDVTQVSSAyQK Y334-p 1.15
## 8 CTTN MDKNASTFEDVTQVSSAyQK Y334-p 1.15
## 9 CTTN nASTFEDVTQVSSAyQk Y334-p 1.15
## 10 DAPP1 KVEEPSIyESVR Y139-p 1.11
## # ℹ 68 more rowsRun_GSEA(DEP_result = dep_E_vs_ctrl_pY, comparison = "E_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "KINASE-PSP_EphA2/EPHA2")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "PATH-NP_EGFR1_PATHWAY"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 12 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 EPHA2 TyVDPHTYEDPNQAVLK Y588-p 0.622
## 2 EPHA2 TYVDPHTyEDPNQAVLK Y594-p 0.314
## 3 EPHA2 tYVDPHTyEDPNQAVLk Y594-p 0.314
## 4 EPHA2 VLEDDPEATyTTSGGK Y772-p 0.310
## 5 EPHA2 VLEDDPEATyTTSGGKIPIR Y772-p 0.310
## 6 EPHA2 vLEDDPEATyTTSGGk Y772-p 0.310
## 7 EPHA2 vLEDDPEATyTTSGGkIPIR Y772-p 0.310
## 8 EPHA2 QSPEDVyFSK Y575-p 0.174
## 9 EPHA2 qSPEDVyFSk Y575-p 0.174
## 10 CLDN4 SAAASNyV Y208-p 0.0688
## 11 CLDN4 sAAASNyV Y208-p 0.0688
## 12 EPHA2 VIGAGEFGEVyKGMLK Y628-p -0.0207EC vs ctrl
data_diff_EC_vs_ctrl_pY <- test_diff(pY_se_Set2, type="manual", test = "EC_vs_ctrl")## Tested contrasts: EC_vs_ctrldep_EC_vs_ctrl_pY <- add_rejections_SH(data_diff_EC_vs_ctrl_pY, alpha = 0.05, lfc = log2(1.2))
GGPlotly_Volcano(dep_EC_vs_ctrl_pY, contrast = "EC_vs_ctrl",
add_names = TRUE,
additional_title = "pY") Return_DEP_Hits_Plots(data = pY_Set2_form, dep_EC_vs_ctrl_pY, comparison = "EC_vs_ctrl_diff")## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns## 'select()' returned 1:1 mapping between keys and columns## character(0)## Warning in min(screen_pval05_neg[, logFcColStr]): no non-missing arguments to
## min; returning Inf## Warning in min(x): no non-missing arguments to min; returning Inf## Warning in max(x): no non-missing arguments to max; returning -Inf## Warning in min(x): no non-missing arguments to min; returning Inf## Warning in max(x): no non-missing arguments to max; returning -Inf## Warning in min(cs1s, na.rm = TRUE): no non-missing arguments to min; returning
## Inf## Warning in max(cs1s, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf## Warning in min(cs2s, na.rm = TRUE): no non-missing arguments to min; returning
## Inf## Warning in max(cs2s, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf## Warning in min(cs3s, na.rm = TRUE): no non-missing arguments to min; returning
## Inf## Warning in max(cs3s, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf
## Note: Row-scaling applied for this heatmap
Plot_Enrichment_Single_Pathway(dep_EC_vs_ctrl_pY, comparison = "EC_vs_ctrl_diff",
pw = "Epigenetic regulation of gene expression")PTM-SEA
GSEA_EC_vs_ctrl_PTM <- Run_GSEA(DEP_result = dep_EC_vs_ctrl_pY, comparison = "EC_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T)## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"GSEA_EC_vs_ctrl_PTM %>% as_tibble() %>% filter(padj < 0.05) %>% arrange(desc(NES))## # A tibble: 1 × 8
## pathway pval padj log2err ES NES size leadingEdge
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <int> <list>
## 1 KINASE-PSP_EphA2/EPHA2 1.84e-5 0.00649 0.576 -0.932 -2.30 6 <chr [6]>Run_GSEA(DEP_result = dep_EC_vs_ctrl_pY, comparison = "EC_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "PATH-NP_EGFR1_PATHWAY")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 254 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 NCK1 LyDLNMPAYVK Y105-p 1.85
## 2 NCK1 lyDLNMPAYVk Y105-p 1.85
## 3 MAPK14 HTDDEMTGyVATR Y182-p 1.53
## 4 MAPK14 HTDDEMtGyVATR Y182-p 1.53
## 5 MAPK14 hTDDEMTGyVATR Y182-p 1.53
## 6 MAPK14 hTDDEMtGyVATR Y182-p 1.53
## 7 MAPK14 hTDDEmTGyVATR Y182-p 1.53
## 8 MAPK14 hTDDEmtGyVATR Y182-p 1.53
## 9 GRB7 DASRPHVVKVySEDGACR Y107-p 1.50
## 10 PXN VGEEEHVySFPNK Y118-p 1.48
## # ℹ 244 more rowsRun_GSEA(DEP_result = dep_EC_vs_ctrl_pY, comparison = "EC_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "KINASE-PSP_Src/SRC")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 78 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 ARHGAP35 NEEENIySVPHDSTQGK Y1105-p 1.80
## 2 ARHGAP35 nEEENIySVPHDSTQGk Y1105-p 1.80
## 3 PRKCD KTGVAGEDMQDNSGTyGK Y334-p 1.30
## 4 PRKCD TGVAGEDMQDNSGTyGK Y334-p 1.30
## 5 PRKCD tGVAGEDMQDNSGTyGk Y334-p 1.30
## 6 SRC EPEERPTFEYLQAFLEDYFTSTEPQyQPGENL Y530-p 1.29
## 7 SRC kEPEERPTFEYLQAFLEDYFTSTEPQyQPGENL Y530-p 1.29
## 8 PRKCD RSDSASSEPVGIyQGFEK Y313-p 1.19
## 9 PRKCD RSDsASSEPVGIyQGFEK Y313-p 1.19
## 10 PRKCD RSDSASSEPVGIyQGFEKK Y313-p 1.19
## # ℹ 68 more rowsRun_GSEA(DEP_result = dep_EC_vs_ctrl_pY, comparison = "EC_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "KINASE-PSP_EphA2/EPHA2")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 12 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 CLDN4 SAAASNyV Y208-p -0.482
## 2 CLDN4 sAAASNyV Y208-p -0.482
## 3 EPHA2 TyVDPHTYEDPNQAVLK Y588-p -0.501
## 4 EPHA2 VIGAGEFGEVyKGMLK Y628-p -0.807
## 5 EPHA2 TYVDPHTyEDPNQAVLK Y594-p -0.877
## 6 EPHA2 tYVDPHTyEDPNQAVLk Y594-p -0.877
## 7 EPHA2 VLEDDPEATyTTSGGK Y772-p -0.968
## 8 EPHA2 VLEDDPEATyTTSGGKIPIR Y772-p -0.968
## 9 EPHA2 vLEDDPEATyTTSGGk Y772-p -0.968
## 10 EPHA2 vLEDDPEATyTTSGGkIPIR Y772-p -0.968
## 11 EPHA2 QSPEDVyFSK Y575-p -1.22
## 12 EPHA2 qSPEDVyFSk Y575-p -1.22EBC vs ctrl
data_diff_EBC_vs_ctrl_pY <- test_diff(pY_se_Set2, type="manual", test = "EBC_vs_ctrl")## Tested contrasts: EBC_vs_ctrldep_EBC_vs_ctrl_pY <- add_rejections_SH(data_diff_EBC_vs_ctrl_pY, alpha = 0.05, lfc = log2(1.2))
GGPlotly_Volcano(dep_EBC_vs_ctrl_pY, contrast = "EBC_vs_ctrl",
add_names = TRUE,
additional_title = "pY")Return_DEP_Hits_Plots(data = pY_Set2_form, dep_EBC_vs_ctrl_pY, comparison = "EBC_vs_ctrl_diff")## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns## 'select()' returned 1:1 mapping between keys and columns## character(0)
## Note: Row-scaling applied for this heatmap
PTM-SEA
GSEA_EBC_vs_ctrl_PTM <- Run_GSEA(DEP_result = dep_EBC_vs_ctrl_pY, comparison = "EBC_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T)## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"GSEA_EBC_vs_ctrl_PTM %>% as_tibble() %>% filter(padj < 0.05) %>% arrange(desc(NES))## # A tibble: 1 × 8
## pathway pval padj log2err ES NES size leadingEdge
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <int> <list>
## 1 KINASE-PSP_EphA2/EPHA2 0.0000378 0.0133 0.557 -0.931 -2.13 6 <chr [5]>Run_GSEA(DEP_result = dep_EBC_vs_ctrl_pY, comparison = "EBC_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "PATH-NP_EGFR1_PATHWAY")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 254 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 GRB7 DASRPHVVKVySEDGACR Y107-p 1.55
## 2 DLG3 DNEVDGQDyHFVVSR Y673-p 1.54
## 3 DLG3 RDNEVDGQDyHFVVSR Y673-p 1.54
## 4 DLG3 dNEVDGQDyHFVVSR Y673-p 1.54
## 5 DLG3 rDNEVDGQDyHFVVSR Y673-p 1.54
## 6 PIK3R2 EYDQLyEEYTR Y464-p 1.44
## 7 PIK3R2 SREYDQLyEEYTR Y464-p 1.44
## 8 PIK3R2 sREYDQLyEEYTR Y464-p 1.44
## 9 NCK1 LyDLNMPAYVK Y105-p 1.41
## 10 NCK1 lyDLNMPAYVk Y105-p 1.41
## # ℹ 244 more rowsRun_GSEA(DEP_result = dep_EBC_vs_ctrl_pY, comparison = "EBC_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "KINASE-PSP_Src/SRC")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 78 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 ARHGAP35 NEEENIySVPHDSTQGK Y1105-p 1.97
## 2 ARHGAP35 nEEENIySVPHDSTQGk Y1105-p 1.97
## 3 SRC EPEERPTFEYLQAFLEDYFTSTEPQyQPGENL Y530-p 1.36
## 4 SRC kEPEERPTFEYLQAFLEDYFTSTEPQyQPGENL Y530-p 1.36
## 5 PTPRA VVQEYIDAFSDyANFK Y798-p 0.777
## 6 PTPRA vVQEYIDAFSDyANFk Y798-p 0.777
## 7 CDH1 yLPRPANPDEIGNFIDENLK Y797-p 0.539
## 8 CDH1 yLPRPANPDEIGNFIDENLk Y797-p 0.539
## 9 PRKCD RSDSASSEPVGIyQGFEK Y313-p 0.525
## 10 PRKCD RSDsASSEPVGIyQGFEK Y313-p 0.525
## # ℹ 68 more rowsRun_GSEA(DEP_result = dep_EBC_vs_ctrl_pY, comparison = "EBC_vs_ctrl_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "KINASE-PSP_EphA2/EPHA2")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 12 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 CLDN4 SAAASNyV Y208-p -0.394
## 2 CLDN4 sAAASNyV Y208-p -0.394
## 3 EPHA2 VIGAGEFGEVyKGMLK Y628-p -0.953
## 4 EPHA2 TyVDPHTYEDPNQAVLK Y588-p -1.05
## 5 EPHA2 VLEDDPEATyTTSGGK Y772-p -1.41
## 6 EPHA2 VLEDDPEATyTTSGGKIPIR Y772-p -1.41
## 7 EPHA2 vLEDDPEATyTTSGGk Y772-p -1.41
## 8 EPHA2 vLEDDPEATyTTSGGkIPIR Y772-p -1.41
## 9 EPHA2 TYVDPHTyEDPNQAVLK Y594-p -1.47
## 10 EPHA2 tYVDPHTyEDPNQAVLk Y594-p -1.47
## 11 EPHA2 QSPEDVyFSK Y575-p -1.80
## 12 EPHA2 qSPEDVyFSk Y575-p -1.80EC vs E
data_diff_EC_vs_E_pY <- test_diff(pY_se_Set2, type = "manual",
test = c("EC_vs_E"))## Tested contrasts: EC_vs_Edep_EC_vs_E_pY <- add_rejections_SH(data_diff_EC_vs_E_pY, alpha = 0.05, lfc = log2(1.2))
GGPlotly_Volcano(dep_EC_vs_E_pY, contrast = "EC_vs_E", add_names = TRUE, additional_title = "pY", proteins_of_interest = "EGFR")Return_DEP_Hits_Plots(data = pY_Set2_form, dep_EC_vs_E_pY, comparison = "EC_vs_E_diff")## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns## 'select()' returned 1:1 mapping between keys and columns## [1] "Metabolism of RNA" "Interleukin-20 family signaling"
## Note: Row-scaling applied for this heatmap
#data_results <- get_df_long(dep)PTM-SEA
GSEA_EC_vs_E_PTM <- Run_GSEA(DEP_result = dep_EC_vs_E_pY, comparison = "EC_vs_E_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T)## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"GSEA_EC_vs_E_PTM %>% as_tibble() %>% filter(padj < 0.05) %>% arrange(desc(NES))## # A tibble: 1 × 8
## pathway pval padj log2err ES NES size leadingEdge
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <int> <list>
## 1 KINASE-PSP_EphA2/EPHA2 1.09e-5 0.00384 0.593 -0.937 -1.89 6 <chr [6]>Run_GSEA(DEP_result = dep_EC_vs_E_pY, comparison = "EC_vs_E_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "PATH-NP_EGFR1_PATHWAY")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 254 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 GRB7 DASRPHVVKVySEDGACR Y107-p 0.991
## 2 SRC EPEERPTFEYLQAFLEDYFTSTEPQyQPGENL Y530-p 0.934
## 3 SRC kEPEERPTFEYLQAFLEDYFTSTEPQyQPGENL Y530-p 0.934
## 4 ITGB4 VCAYGAQGEGPySSLVSCR Y1207-p 0.483
## 5 ITGB4 vcAYGAQGEGPySSLVScR Y1207-p 0.483
## 6 PRKCD RSDSASSEPVGIyQGFEK Y313-p 0.482
## 7 PRKCD RSDsASSEPVGIyQGFEK Y313-p 0.482
## 8 PRKCD RSDSASSEPVGIyQGFEKK Y313-p 0.482
## 9 PRKCD SDSASSEPVGIyQGFEK Y313-p 0.482
## 10 PRKCD SDsASSEPVGIyQGFEK Y313-p 0.482
## # ℹ 244 more rowsRun_GSEA(DEP_result = dep_EC_vs_E_pY, comparison = "EC_vs_E_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "KINASE-PSP_Src/SRC")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 78 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 ARHGAP35 NEEENIySVPHDSTQGK Y1105-p 1.31
## 2 ARHGAP35 nEEENIySVPHDSTQGk Y1105-p 1.31
## 3 SRC EPEERPTFEYLQAFLEDYFTSTEPQyQPGENL Y530-p 0.934
## 4 SRC kEPEERPTFEYLQAFLEDYFTSTEPQyQPGENL Y530-p 0.934
## 5 PRKCD RSDSASSEPVGIyQGFEK Y313-p 0.482
## 6 PRKCD RSDsASSEPVGIyQGFEK Y313-p 0.482
## 7 PRKCD RSDSASSEPVGIyQGFEKK Y313-p 0.482
## 8 PRKCD SDSASSEPVGIyQGFEK Y313-p 0.482
## 9 PRKCD SDsASSEPVGIyQGFEK Y313-p 0.482
## 10 PRKCD SDSASSEPVGIyQGFEKK Y313-p 0.482
## # ℹ 68 more rowsRun_GSEA(DEP_result = dep_EC_vs_E_pY, comparison = "EC_vs_E_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "KINASE-PSP_EphA2/EPHA2")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "KINASE-PSP_EphA2/EPHA2"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 12 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 CLDN4 SAAASNyV Y208-p -0.551
## 2 CLDN4 sAAASNyV Y208-p -0.551
## 3 EPHA2 VIGAGEFGEVyKGMLK Y628-p -0.786
## 4 EPHA2 TyVDPHTYEDPNQAVLK Y588-p -1.12
## 5 EPHA2 TYVDPHTyEDPNQAVLK Y594-p -1.19
## 6 EPHA2 tYVDPHTyEDPNQAVLk Y594-p -1.19
## 7 EPHA2 VLEDDPEATyTTSGGK Y772-p -1.28
## 8 EPHA2 VLEDDPEATyTTSGGKIPIR Y772-p -1.28
## 9 EPHA2 vLEDDPEATyTTSGGk Y772-p -1.28
## 10 EPHA2 vLEDDPEATyTTSGGkIPIR Y772-p -1.28
## 11 EPHA2 QSPEDVyFSK Y575-p -1.39
## 12 EPHA2 qSPEDVyFSk Y575-p -1.39EBC vs EC
data_diff_EBC_vs_EC_pY <- test_diff(pY_se_Set2, type = "manual",
test = c("EBC_vs_EC"))## Tested contrasts: EBC_vs_ECdep_EBC_vs_EC_pY <- add_rejections_SH(data_diff_EBC_vs_EC_pY, alpha = 0.05, lfc = log2(1.2))
GGPlotly_Volcano(dep_EBC_vs_EC_pY, contrast = "EBC_vs_EC", add_names = TRUE, additional_title = "pY")Return_DEP_Hits_Plots(data = pY_Set2_form, dep_EBC_vs_EC_pY, comparison = "EBC_vs_EC_diff")## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns## 'select()' returned 1:1 mapping between keys and columns
## [1] "Metabolism of nucleotides" "Selenoamino acid metabolism"
## [3] "Metabolism" "Signaling by VEGF"#data_results <- get_df_long(dep)PTM-SEA
GSEA_EBC_vs_EC_PTM <- Run_GSEA(DEP_result = dep_EBC_vs_EC_pY, comparison = "EBC_vs_EC_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T)## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "PATH-NP_EGFR1_PATHWAY"GSEA_EBC_vs_EC_PTM %>% as_tibble() %>% filter(padj < 0.05) %>% arrange(desc(NES))## # A tibble: 1 × 8
## pathway pval padj log2err ES NES size leadingEdge
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <int> <list>
## 1 PATH-NP_EGFR1_PATHWAY 0.0000775 0.0273 0.538 -0.501 -1.64 116 <chr [39]>Run_GSEA(DEP_result = dep_EBC_vs_EC_pY, comparison = "EBC_vs_EC_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "PATH-NP_EGFR1_PATHWAY")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "PATH-NP_EGFR1_PATHWAY"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 254 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 CDK5 IGEGTyGTVFK Y15-p 0.759
## 2 ATP1A1 GIVVyTGDR Y260-p 0.627
## 3 PIK3R1 DQyLMWLTQK Y580-p 0.530
## 4 PIK3R1 TRDQyLMWLTQK Y580-p 0.530
## 5 PIK3R1 dQyLMWLTQk Y580-p 0.530
## 6 PIK3R1 dQyLmWLTQk Y580-p 0.530
## 7 DLG3 DNEVDGQDyHFVVSR Y673-p 0.452
## 8 DLG3 RDNEVDGQDyHFVVSR Y673-p 0.452
## 9 DLG3 dNEVDGQDyHFVVSR Y673-p 0.452
## 10 DLG3 rDNEVDGQDyHFVVSR Y673-p 0.452
## # ℹ 244 more rowsRun_GSEA(DEP_result = dep_EBC_vs_EC_pY, comparison = "EBC_vs_EC_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "KINASE-PSP_Src/SRC")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "PATH-NP_EGFR1_PATHWAY"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 78 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 ATP1A1 GIVVyTGDR Y260-p 0.627
## 2 DDR2 NLySGDYYR Y736-p 0.219
## 3 DDR2 NLySGDyYR Y736-p 0.219
## 4 STAT3 YCRPESQEHPEADPGSAAPyLK Y705-p 0.192
## 5 ARHGAP35 NEEENIySVPHDSTQGK Y1105-p 0.168
## 6 ARHGAP35 nEEENIySVPHDSTQGk Y1105-p 0.168
## 7 SDC4 APTNEFyA Y197-p 0.142
## 8 SDC4 KAPTNEFyA Y197-p 0.142
## 9 PTK2 SNDKVyENVTGLVK Y925-p 0.0905
## 10 SRC EPEERPTFEYLQAFLEDYFTSTEPQyQPGENL Y530-p 0.0657
## # ℹ 68 more rowsRun_GSEA(DEP_result = dep_EBC_vs_EC_pY, comparison = "EBC_vs_EC_diff", return_df = T,
ptmGSEA_site_df = all_pY_sites, PtmSigdb = PtmSigdb, ptmGSEA = T, single_pathway = "KINASE-PSP_EphA2/EPHA2")## Joining with `by = join_by(HGNC_Symbol, Annotated_Sequence)`## [1] "PATH-NP_EGFR1_PATHWAY"## Joining with `by = join_by(SITE_GRP_ID)`
## # A tibble: 12 × 4
## HGNC_Symbol Annotated_Sequence MOD_RSD FC
## <chr> <chr> <chr> <dbl>
## 1 CLDN4 SAAASNyV Y208-p 0.0884
## 2 CLDN4 sAAASNyV Y208-p 0.0884
## 3 EPHA2 VIGAGEFGEVyKGMLK Y628-p -0.146
## 4 EPHA2 VLEDDPEATyTTSGGK Y772-p -0.441
## 5 EPHA2 VLEDDPEATyTTSGGKIPIR Y772-p -0.441
## 6 EPHA2 vLEDDPEATyTTSGGk Y772-p -0.441
## 7 EPHA2 vLEDDPEATyTTSGGkIPIR Y772-p -0.441
## 8 EPHA2 TyVDPHTYEDPNQAVLK Y588-p -0.547
## 9 EPHA2 QSPEDVyFSK Y575-p -0.577
## 10 EPHA2 qSPEDVyFSk Y575-p -0.577
## 11 EPHA2 TYVDPHTyEDPNQAVLK Y594-p -0.590
## 12 EPHA2 tYVDPHTyEDPNQAVLk Y594-p -0.590Serine/Threonine
Each condition vs ctrl
data_diff_E_vs_ctrl_pST <- test_diff(pST_se_Set2, type="manual", test = "E_vs_ctrl")## Tested contrasts: E_vs_ctrldep_E_vs_ctrl_pST <- add_rejections_SH(data_diff_E_vs_ctrl_pST, alpha = 0.05, lfc = log2(1.2))
GGPlotly_Volcano(dep_E_vs_ctrl_pST, contrast = "E_vs_ctrl",
add_names = TRUE,
additional_title = "pST") Return_DEP_Hits_Plots(data = pST_Set2_form, dep_E_vs_ctrl_pST, comparison = "E_vs_ctrl_diff")## 'select()' returned 1:1 mapping between keys and columns## 'select()' returned 1:many mapping between keys and columns## 'select()' returned 1:1 mapping between keys and columns
## character(0)data_diff_EC_vs_ctrl_pST <- test_diff(pST_se_Set2, type="manual", test = "EC_vs_ctrl")## Tested contrasts: EC_vs_ctrldep_EC_vs_ctrl_pST <- add_rejections_SH(data_diff_EC_vs_ctrl_pST, alpha = 0.05, lfc = log2(1.2))
GGPlotly_Volcano(dep_EC_vs_ctrl_pST, contrast = "EC_vs_ctrl",
add_names = TRUE,
additional_title = "pST") Return_DEP_Hits_Plots(data = pST_Set2_form, dep_EC_vs_ctrl_pST, comparison = "EC_vs_ctrl_diff")## 'select()' returned 1:1 mapping between keys and columns## 'select()' returned 1:many mapping between keys and columns## 'select()' returned 1:1 mapping between keys and columns
## character(0)Plot_Enrichment_Single_Pathway(dep_EC_vs_ctrl_pST, comparison = "EC_vs_ctrl_diff",
pw = "Epigenetic regulation of gene expression")data_diff_EBC_vs_ctrl_pST <- test_diff(pST_se_Set2, type="manual", test = "EBC_vs_ctrl")## Tested contrasts: EBC_vs_ctrldep_EBC_vs_ctrl_pST <- add_rejections_SH(data_diff_EBC_vs_ctrl_pST, alpha = 0.05, lfc = log2(1.2))
GGPlotly_Volcano(dep_EBC_vs_ctrl_pST, contrast = "EBC_vs_ctrl",
add_names = TRUE,
additional_title = "pST")Return_DEP_Hits_Plots(data = pST_Set2_form, dep_EBC_vs_ctrl_pST, comparison = "EBC_vs_ctrl_diff")## 'select()' returned 1:1 mapping between keys and columns## 'select()' returned 1:many mapping between keys and columns## 'select()' returned 1:1 mapping between keys and columns
## [1] "Metabolism of RNA"EC vs E
data_diff_EC_vs_E_pST <- test_diff(pST_se_Set2, type = "manual",
test = c("EC_vs_E"))## Tested contrasts: EC_vs_Edep_EC_vs_E_pST <- add_rejections_SH(data_diff_EC_vs_E_pST, alpha = 0.05, lfc = log2(1.2))
GGPlotly_Volcano(dep_EC_vs_E_pST, contrast = "EC_vs_E", add_names = TRUE, additional_title = "pST", proteins_of_interest = "EGFR")Return_DEP_Hits_Plots(data = pST_Set2_form, dep_EC_vs_E_pST, comparison = "EC_vs_E_diff")## 'select()' returned 1:1 mapping between keys and columns## 'select()' returned 1:many mapping between keys and columns## 'select()' returned 1:1 mapping between keys and columns## character(0)
## Note: Row-scaling applied for this heatmap
#data_results <- get_df_long(dep)EBC vs EC
data_diff_EBC_vs_EC_pST <- test_diff(pST_se_Set2, type = "manual",
test = c("EBC_vs_EC"))## Tested contrasts: EBC_vs_ECdep_EBC_vs_EC_pST <- add_rejections_SH(data_diff_EBC_vs_EC_pST, alpha = 0.05, lfc = log2(1.2))
GGPlotly_Volcano(dep_EBC_vs_EC_pST, contrast = "EBC_vs_EC", add_names = TRUE, additional_title = "pST")Return_DEP_Hits_Plots(data = pST_Set2_form, dep_EBC_vs_EC_pST, comparison = "EBC_vs_EC_diff")## 'select()' returned 1:1 mapping between keys and columns## 'select()' returned 1:many mapping between keys and columns## 'select()' returned 1:1 mapping between keys and columns
## [1] "Metabolism of RNA"#data_results <- get_df_long(dep)For Phosphosite Plus kinase enrichment
EC_vs_ctrl_pST_7AA <- left_join( (rowData(dep_EC_vs_ctrl_pST) %>% as_tibble() %>%
#filter(LTB4_vs_ctrl_p.adj< 0.05, LTB4_vs_ctrl_diff > 1.2) %>%
select(annotation = ID, Annotated_Sequence, HGNC_Symbol, fc = EC_vs_ctrl_diff, p = EC_vs_ctrl_p.adj) %>% unique ),
(all_pST_sites %>% select(Annotated_Sequence, Sequence_7_AA, HGNC_Symbol)),
by=c("Annotated_Sequence", "HGNC_Symbol") ) %>% filter(!is.na(Sequence_7_AA)) %>%
mutate( peptide = str_to_upper(Sequence_7_AA) ) %>%
select(annotation, peptide, fc, p) %>% as.data.frame()Save
EC_vs_ctrl_pST_7AA %>% select(peptide, fc, p) %>% write.table(file = "../Data/Kinase_enrichment/Batch2_Set2_EC_vs_ctrl_pST_7AA.txt", quote = FALSE, row.names = F, col.names = F, sep = "\t")
rowData(dep_EC_vs_ctrl_pY) %>% as_tibble() %>%
filter(EC_vs_ctrl_diff>1) %>%
select(HGNC_Symbol ) %>% unique() %>%
write.table("../Data/Kinase_enrichment/Batch2_Set2_EC_vs_ctrl_pY_FCmorethan1_forstring.txt", quote = F, row.names = F, col.names = F, sep = "\t")Session Info
sessionInfo()## R version 4.2.3 (2023-03-15)
## Platform: x86_64-apple-darwin17.0 (64-bit)
## Running under: macOS Big Sur ... 10.16
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.2/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.2/Resources/lib/libRlapack.dylib
##
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## attached base packages:
## [1] stats4 stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] lubridate_1.9.2 forcats_1.0.0
## [3] stringr_1.5.0 dplyr_1.1.2
## [5] purrr_1.0.2 readr_2.1.4
## [7] tidyr_1.3.0 tibble_3.2.1
## [9] ggplot2_3.4.2 tidyverse_2.0.0
## [11] mdatools_0.14.0 SummarizedExperiment_1.28.0
## [13] GenomicRanges_1.50.2 GenomeInfoDb_1.34.9
## [15] MatrixGenerics_1.10.0 matrixStats_1.0.0
## [17] DEP_1.20.0 org.Hs.eg.db_3.16.0
## [19] AnnotationDbi_1.60.2 IRanges_2.32.0
## [21] S4Vectors_0.36.2 Biobase_2.58.0
## [23] BiocGenerics_0.44.0 fgsea_1.24.0
##
## loaded via a namespace (and not attached):
## [1] circlize_0.4.15 fastmatch_1.1-4 plyr_1.8.8
## [4] igraph_1.5.1 gmm_1.8 lazyeval_0.2.2
## [7] shinydashboard_0.7.2 crosstalk_1.2.0 BiocParallel_1.32.6
## [10] digest_0.6.33 foreach_1.5.2 htmltools_0.5.6
## [13] fansi_1.0.4 magrittr_2.0.3 memoise_2.0.1
## [16] cluster_2.1.4 doParallel_1.0.17 tzdb_0.4.0
## [19] limma_3.54.2 ComplexHeatmap_2.14.0 Biostrings_2.66.0
## [22] imputeLCMD_2.1 sandwich_3.0-2 timechange_0.2.0
## [25] colorspace_2.1-0 blob_1.2.4 xfun_0.40
## [28] crayon_1.5.2 RCurl_1.98-1.12 jsonlite_1.8.7
## [31] impute_1.72.3 zoo_1.8-12 iterators_1.0.14
## [34] glue_1.6.2 hash_2.2.6.2 gtable_0.3.3
## [37] zlibbioc_1.44.0 XVector_0.38.0 GetoptLong_1.0.5
## [40] DelayedArray_0.24.0 shape_1.4.6 scales_1.2.1
## [43] pheatmap_1.0.12 vsn_3.66.0 mvtnorm_1.2-2
## [46] DBI_1.1.3 Rcpp_1.0.11 plotrix_3.8-2
## [49] mzR_2.32.0 viridisLite_0.4.2 xtable_1.8-4
## [52] clue_0.3-64 reactome.db_1.82.0 bit_4.0.5
## [55] preprocessCore_1.60.2 sqldf_0.4-11 MsCoreUtils_1.10.0
## [58] DT_0.28 htmlwidgets_1.6.2 httr_1.4.6
## [61] gplots_3.1.3 RColorBrewer_1.1-3 ellipsis_0.3.2
## [64] farver_2.1.1 pkgconfig_2.0.3 XML_3.99-0.14
## [67] sass_0.4.7 utf8_1.2.3 STRINGdb_2.10.1
## [70] labeling_0.4.2 tidyselect_1.2.0 rlang_1.1.1
## [73] later_1.3.1 munsell_0.5.0 tools_4.2.3
## [76] cachem_1.0.8 cli_3.6.1 gsubfn_0.7
## [79] generics_0.1.3 RSQLite_2.3.1 fdrtool_1.2.17
## [82] evaluate_0.21 fastmap_1.1.1 mzID_1.36.0
## [85] yaml_2.3.7 knitr_1.43 bit64_4.0.5
## [88] caTools_1.18.2 KEGGREST_1.38.0 ncdf4_1.21
## [91] mime_0.12 compiler_4.2.3 rstudioapi_0.15.0
## [94] plotly_4.10.2 png_0.1-8 affyio_1.68.0
## [97] stringi_1.7.12 bslib_0.5.0 highr_0.10
## [100] MSnbase_2.24.2 lattice_0.21-8 ProtGenerics_1.30.0
## [103] Matrix_1.6-0 tmvtnorm_1.5 vctrs_0.6.3
## [106] pillar_1.9.0 norm_1.0-11.1 lifecycle_1.0.3
## [109] BiocManager_1.30.22 jquerylib_0.1.4 MALDIquant_1.22.1
## [112] GlobalOptions_0.1.2 data.table_1.14.8 cowplot_1.1.1
## [115] bitops_1.0-7 httpuv_1.6.11 R6_2.5.1
## [118] pcaMethods_1.90.0 affy_1.76.0 promises_1.2.1
## [121] KernSmooth_2.23-22 codetools_0.2-19 MASS_7.3-60
## [124] gtools_3.9.4 assertthat_0.2.1 chron_2.3-61
## [127] proto_1.0.0 rjson_0.2.21 withr_2.5.0
## [130] GenomeInfoDbData_1.2.9 parallel_4.2.3 hms_1.1.3
## [133] grid_4.2.3 rmarkdown_2.23 shiny_1.7.4.1knitr::knit_exit()